Paper Group NANR 244
Network Global Testing by Counting Graphlets. The Limits of Maxing, Ranking, and Preference Learning. Integrating Entity Linking and Evidence Ranking for Fact Extraction and Verification. Coupled End-to-End Transfer Learning With Generalized Fisher Information. Capturing Human Category Representations by Sampling in Deep Feature Spaces. A Practical …
Network Global Testing by Counting Graphlets
| Title | Network Global Testing by Counting Graphlets |
| Authors | Jiashun Jin, Zheng Ke, Shengming Luo |
| Abstract | Consider a large social network with possibly severe degree heterogeneity and mixed-memberships. We are interested in testing whether the network has only one community or there are more than one communities. The problem is known to be non-trivial, partially due to the presence of severe degree heterogeneity. We construct a class of test statistics using the numbers of short paths and short cycles, and the key to our approach is a general framework for canceling the effects of degree heterogeneity. The tests compare favorably with existing methods. We support our methods with careful analysis and numerical study with simulated data and a real data example. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2338 |
| http://proceedings.mlr.press/v80/jin18b/jin18b.pdf | |
| PWC | https://paperswithcode.com/paper/network-global-testing-by-counting-graphlets |
| Repo | |
| Framework | |
The Limits of Maxing, Ranking, and Preference Learning
| Title | The Limits of Maxing, Ranking, and Preference Learning |
| Authors | Moein Falahatgar, Ayush Jain, Alon Orlitsky, Venkatadheeraj Pichapati, Vaishakh Ravindrakumar |
| Abstract | We present a comprehensive understanding of three important problems in PAC preference learning: maximum selection (maxing), ranking, and estimating all pairwise preference probabilities, in the adaptive setting. With just Weak Stochastic Transitivity, we show that maxing requires $\Omega(n^2)$ comparisons and with slightly more restrictive Medium Stochastic Transitivity, we present a linear complexity maxing algorithm. With Strong Stochastic Transitivity and Stochastic Triangle Inequality, we derive a ranking algorithm with optimal $\mathcal{O}(n\log n)$ complexity and an optimal algorithm that estimates all pairwise preference probabilities. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2103 |
| http://proceedings.mlr.press/v80/falahatgar18a/falahatgar18a.pdf | |
| PWC | https://paperswithcode.com/paper/the-limits-of-maxing-ranking-and-preference |
| Repo | |
| Framework | |
Integrating Entity Linking and Evidence Ranking for Fact Extraction and Verification
| Title | Integrating Entity Linking and Evidence Ranking for Fact Extraction and Verification |
| Authors | Motoki Taniguchi, Tomoki Taniguchi, Takumi Takahashi, Yasuhide Miura, Tomoko Ohkuma |
| Abstract | We describe here our system and results on the FEVER shared task. We prepared a pipeline system which composes of a document selection, a sentence retrieval, and a recognizing textual entailment (RTE) components. A simple entity linking approach with text match is used as the document selection component, this component identifies relevant documents for a given claim by using mentioned entities as clues. The sentence retrieval component selects relevant sentences as candidate evidence from the documents based on TF-IDF. Finally, the RTE component selects evidence sentences by ranking the sentences and classifies the claim simultaneously. The experimental results show that our system achieved the FEVER score of 0.4016 and outperformed the official baseline system. |
| Tasks | Entity Linking, Natural Language Inference |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5520/ |
| https://www.aclweb.org/anthology/W18-5520 | |
| PWC | https://paperswithcode.com/paper/integrating-entity-linking-and-evidence |
| Repo | |
| Framework | |
Coupled End-to-End Transfer Learning With Generalized Fisher Information
| Title | Coupled End-to-End Transfer Learning With Generalized Fisher Information |
| Authors | Shixing Chen, Caojin Zhang, Ming Dong |
| Abstract | In transfer learning, one seeks to transfer related information from source tasks with sufficient data to help with the learning of target task with only limited data. In this paper, we propose a novel Coupled End-to-end Transfer Learning (CETL) framework, which mainly consists of two convolutional neural networks (source and target) that connect to a shared decoder. A novel loss function, the coupled loss, is used for CETL training. From a theoretical perspective, we demonstrate the rationale of the coupled loss by establishing a learning bound for CETL. Moreover, we introduce the generalized Fisher information to improve multi-task optimization in CETL. From a practical aspect, CETL provides a unified and highly flexible solution for various learning tasks such as domain adaption and knowledge distillation. Empirical result shows the superior performance of CETL on cross-domain and cross-task image classification. |
| Tasks | Domain Adaptation, Image Classification, Transfer Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Chen_Coupled_End-to-End_Transfer_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Coupled_End-to-End_Transfer_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/coupled-end-to-end-transfer-learning-with |
| Repo | |
| Framework | |
Capturing Human Category Representations by Sampling in Deep Feature Spaces
| Title | Capturing Human Category Representations by Sampling in Deep Feature Spaces |
| Authors | Joshua Peterson, Krishan Aghi, Jordan Suchow, Alexander Ku, Tom Griffiths |
| Abstract | Understanding how people represent categories is a core problem in cognitive science, with the flexibility of human learning remaining a gold standard to which modern artificial intelligence and machine learning aspire. Decades of psychological research have yielded a variety of formal theories of categories, yet validating these theories with naturalistic stimuli remains a challenge. The problem is that human category representations cannot be directly observed and running informative experiments with naturalistic stimuli such as images requires having a workable representation of these stimuli. Deep neural networks have recently been successful in a range of computer vision tasks and provide a way to represent the features of images. In this paper, we introduce a method for estimating the structure of human categories that draws on ideas from both cognitive science and machine learning, blending human-based algorithms with state-of-the-art deep representation learners. We provide qualitative and quantitative results as a proof of concept for the feasibility of the method. Samples drawn from human distributions rival the quality of current state-of-the-art generative models and outperform alternative methods for estimating the structure of human categories. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJy0fcgRZ |
| https://openreview.net/pdf?id=BJy0fcgRZ | |
| PWC | https://paperswithcode.com/paper/capturing-human-category-representations-by-1 |
| Repo | |
| Framework | |
A Practical Deep Online Ranking System in E-commerce Recommendation
| Title | A Practical Deep Online Ranking System in E-commerce Recommendation |
| Authors | Yan Yan1, Zitao Liu2, Meng Zhao1, Wentao Guo1, Weipeng P. Yan1, and Yongjun Bao1 |
| Abstract | User online shopping experience in modern e-commerce websites critically relies on real-time personalized recommendations. However, building a productionized recommender system still remains challenging due to a massive collection of items, a huge number of online users, and requirements for recommendations to be responsive to user actions. In this work, we present our relevant, responsive, and scalable deep online ranking system (DORS) that we developed and deployed in our company. DORS is implemented in a three-level architecture which includes (1) candidate retrieval that retrieves a board set of candidates with various business rules enforced; (2) deep neural network ranking model that takes advantage of available user and item specific features and their interactions; (3) multi-arm bandits based online re-ranking that dynamically takes user real-time feedback and re-ranks the final recommended items in scale. Given a user as a query, DORS is able to precisely capture users’ real-time purchasing intents and help users reach to product purchases. Both offline and online experimental results show that DORS provides more personalized online ranking results and makes more revenue. |
| Tasks | Recommendation Systems |
| Published | 2018-09-01 |
| URL | http://www.ecmlpkdd2018.org/wp-content/uploads/2018/09/723.pdf |
| http://www.ecmlpkdd2018.org/wp-content/uploads/2018/09/723.pdf | |
| PWC | https://paperswithcode.com/paper/a-practical-deep-online-ranking-system-in-e |
| Repo | |
| Framework | |
Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms
| Title | Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms |
| Authors | Charlie Dickens, Graham Cormode, David Woodruff |
| Abstract | Work on approximate linear algebra has led to efficient distributed and streaming algorithms for problems such as approximate matrix multiplication, low rank approximation, and regression, primarily for the Euclidean norm $\ell_2$. We study other $\ell_p$ norms, which are more robust for $p < 2$, and can be used to find outliers for $p > 2$. Unlike previous algorithms for such norms, we give algorithms that are (1) deterministic, (2) work simultaneously for every $p \geq 1$, including $p = \infty$, and (3) can be implemented in both distributed and streaming environments. We study $\ell_p$-regression, entrywise $\ell_p$-low rank approximation, and versions of approximate matrix multiplication. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2163 |
| http://proceedings.mlr.press/v80/dickens18a/dickens18a.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-well-conditioned-bases-streaming |
| Repo | |
| Framework | |
SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network
| Title | SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network |
| Authors | Yancheng Bai, Yongqiang Zhang, Mingli Ding, Bernard Ghanem |
| Abstract | Object detection is a fundamental and important problem in computer vision. Although impressive results have been achieved on large/medium sized objects on large-scale detection benchmarks (e.g. the COCO dataset), the performance on small objects is far from satisfaction. The reason is that small objects lack sufficient detailed appearance information, which can distinguish them from the background or similar objects. To deal with small object detection problem, we propose an end-to-end multi-task generative adversarial network (MTGAN). In the MTGAN, the generator is a super-resolution network, which can up-sample small blurred images into fine-scale ones and recover detailed information for more accurate detection. The discriminator is a multi task network, which describes each super-resolution image patch with a real/fake score, object category scores, and bounding box regression off sets. Furthermore, to make the generator recover more details for easier detection, the classification and regression losses in the discriminator are back-propagated into the generator during training. Extensive experiments on the challenging COCO dataset demonstrate the effectiveness of the proposed method in restoring a clear super-resolution image from a blurred small one, and show that the detection performance, especially for small sized objects, improves over state-of-the-art methods. |
| Tasks | Object Detection, Small Object Detection, Super-Resolution |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yongqiang_Zhang_SOD-MTGAN_Small_Object_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yongqiang_Zhang_SOD-MTGAN_Small_Object_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sod-mtgan-small-object-detection-via-multi |
| Repo | |
| Framework | |
Stochastic Proximal Algorithms for AUC Maximization
| Title | Stochastic Proximal Algorithms for AUC Maximization |
| Authors | Michael Natole, Yiming Ying, Siwei Lyu |
| Abstract | Stochastic optimization algorithms such as SGDs update the model sequentially with cheap per-iteration costs, making them amenable for large-scale data analysis. However, most of the existing studies focus on the classification accuracy which can not be directly applied to the important problems of maximizing the Area under the ROC curve (AUC) in imbalanced classification and bipartite ranking. In this paper, we develop a novel stochastic proximal algorithm for AUC maximization which is referred to as SPAM. Compared with the previous literature, our algorithm SPAM applies to a non-smooth penalty function, and achieves a convergence rate of O(log t/t) for strongly convex functions while both space and per-iteration costs are of one datum. |
| Tasks | Stochastic Optimization |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1921 |
| http://proceedings.mlr.press/v80/natole18a/natole18a.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-proximal-algorithms-for-auc |
| Repo | |
| Framework | |
An Ensemble Approach for Aggression Identification in English and Hindi Text
| Title | An Ensemble Approach for Aggression Identification in English and Hindi Text |
| Authors | Arjun Roy, Prashant Kapil, Kingshuk Basak, Asif Ekbal |
| Abstract | This paper describes our system submitted in the shared task at COLING 2018 TRAC-1: Aggression Identification. The objective of this task was to predict online aggression spread through online textual post or comment. The dataset was released in two languages, English and Hindi. We submitted a single system for Hindi and a single system for English. Both the systems are based on an ensemble architecture where the individual models are based on Convoluted Neural Network and Support Vector Machine. Evaluation shows promising results for both the languages.The total submission for English was 30 and Hindi was 15. Our system on English facebook and social media obtained F1 score of 0.5151 and 0.5099 respectively where Hindi facebook and social media obtained F1 score of 0.5599 and 0.3790 respectively. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4408/ |
| https://www.aclweb.org/anthology/W18-4408 | |
| PWC | https://paperswithcode.com/paper/an-ensemble-approach-for-aggression |
| Repo | |
| Framework | |
Find and Focus: Retrieve and Localize Video Events with Natural Language Queries
| Title | Find and Focus: Retrieve and Localize Video Events with Natural Language Queries |
| Authors | Dian Shao, Yu Xiong, Yue Zhao, Qingqiu Huang, Yu Qiao, Dahua Lin |
| Abstract | The thriving of video sharing services brings new challenges to video retrieval, e.g. the rapid growth in video duration and content diversity. Meeting such challenges calls for new techniques that can effectively retrieve videos with natural language queries. Existing methods along this line, which mostly rely on embedding videos as a whole, remain far from satisfactory for real-world applications due to the limited expressive power. In this work, we aim to move beyond this limitation by delving into the internal structures of both sides, the queries and the videos. Specifically, we propose a new framework called Find and Focus (FIFO), which not only performs top-level matching (paragraph vs. video), but also makes part-level associations, localizing a video clip for each sentence in the query with the help of a focusing guide. These levels are complementary - the top-level matching narrows the search while the part-level localization refines the results. On both ActivityNet Captions and modified LSMDC datasets, the proposed framework achieves remarkable performance gains. |
| Tasks | Video Retrieval |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Dian_SHAO_Find_and_Focus_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Dian_SHAO_Find_and_Focus_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/find-and-focus-retrieve-and-localize-video |
| Repo | |
| Framework | |
Detecting Diabetes Risk from Social Media Activity
| Title | Detecting Diabetes Risk from Social Media Activity |
| Authors | Dane Bell, Egoitz Laparra, Aditya Kousik, Terron Ishihara, Mihai Surdeanu, Stephen Kobourov |
| Abstract | This work explores the detection of individuals{'} risk of type 2 diabetes mellitus (T2DM) directly from their social media (Twitter) activity. Our approach extends a deep learning architecture with several contributions: following previous observations that language use differs by gender, it captures and uses gender information through domain adaptation; it captures recency of posts under the hypothesis that more recent posts are more representative of an individual{'}s current risk status; and, lastly, it demonstrates that in this scenario where activity factors are sparsely represented in the data, a bag-of-word neural network model using custom dictionaries of food and activity words performs better than other neural sequence models. Our best model, which incorporates all these contributions, achieves a risk-detection F1 of 41.9, considerably higher than the baseline rate (36.9). |
| Tasks | Domain Adaptation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5601/ |
| https://www.aclweb.org/anthology/W18-5601 | |
| PWC | https://paperswithcode.com/paper/detecting-diabetes-risk-from-social-media |
| Repo | |
| Framework | |
Generating Syntactic Paraphrases
| Title | Generating Syntactic Paraphrases |
| Authors | Emilie Colin, Claire Gardent |
| Abstract | We study the automatic generation of syntactic paraphrases using four different models for generation: data-to-text generation, text-to-text generation, text reduction and text expansion, We derive training data for each of these tasks from the WebNLG dataset and we show (i) that conditioning generation on syntactic constraints effectively permits the generation of syntactically distinct paraphrases for the same input and (ii) that exploiting different types of input (data, text or data+text) further increases the number of distinct paraphrases that can be generated for a given input. |
| Tasks | Data-to-Text Generation, Machine Translation, Paraphrase Generation, Question Answering, Semantic Parsing, Sentence Compression, Text Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1113/ |
| https://www.aclweb.org/anthology/D18-1113 | |
| PWC | https://paperswithcode.com/paper/generating-syntactic-paraphrases |
| Repo | |
| Framework | |
ESCRITO - An NLP-Enhanced Educational Scoring Toolkit
| Title | ESCRITO - An NLP-Enhanced Educational Scoring Toolkit |
| Authors | Torsten Zesch, Andrea Horbach |
| Abstract | |
| Tasks | Argument Mining, Grammatical Error Correction, Natural Language Inference, Text Classification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1365/ |
| https://www.aclweb.org/anthology/L18-1365 | |
| PWC | https://paperswithcode.com/paper/escrito-an-nlp-enhanced-educational-scoring |
| Repo | |
| Framework | |
Weakly Supervised Learning of Single-Cell Feature Embeddings
| Title | Weakly Supervised Learning of Single-Cell Feature Embeddings |
| Authors | Juan C. Caicedo, Claire McQuin, Allen Goodman, Shantanu Singh, Anne E. Carpenter |
| Abstract | Many new applications in drug discovery and functional genomics require capturing the morphology of individual imaged cells as comprehensively as possible rather than measuring one particular feature. In these so-called profiling experiments, the goal is to compare populations of cells treated with different chemicals or genetic perturbations in order to identify biomedically important similarities. Deep convolutional neural networks (CNNs) often make excellent feature extractors but require ground truth for training; this is rarely available in biomedical profiling experiments. We therefore propose to train CNNs based on a weakly supervised approach, where the network aims to classify each treatment against all others. Using this network as a feature extractor performed comparably to a network trained on non-biological, natural images on a chemical screen benchmark task, and improved results significantly on a more challenging genetic benchmark presented for the first time. |
| Tasks | Drug Discovery |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Caicedo_Weakly_Supervised_Learning_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Caicedo_Weakly_Supervised_Learning_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-learning-of-single-cell |
| Repo | |
| Framework | |
